Restrict sysroot crate imports to those defined in this repo.

It's common to import dependencies from the sysroot via `extern crate`
rather than use an explicit cargo dependency, when it's necessary to use
the same dependency version as used by rustc itself. However, this is
dangerous for crates.io crates, since rustc may not pull in the
dependency on some targets, or may pull in multiple versions. In both
cases, the `extern crate` fails to resolve.

To address this, re-export all such dependencies from the appropriate
`rustc_*` crates, and use this alias from crates which would otherwise
need to use `extern crate`.

Author: Diggsey

Cargo.lock

@@ -4119,6 +4119,7 @@ name = "rustc_log"
 version = "0.0.0"
 dependencies = [
  "tracing",
+ "tracing-core",
  "tracing-subscriber",
  "tracing-tree",
 ]

compiler/rustc_codegen_cranelift/src/lib.rs

@@ -26,13 +26,12 @@ extern crate rustc_fs_util;
 extern crate rustc_hir;
 extern crate rustc_incremental;
 extern crate rustc_index;
+extern crate rustc_log;
 extern crate rustc_metadata;
 extern crate rustc_session;
 extern crate rustc_span;
 extern crate rustc_symbol_mangling;
 extern crate rustc_target;
-#[macro_use]
-extern crate tracing;
 
 // This prevents duplicating functions and statics that are already part of the host rustc process.
 #[allow(unused_extern_crates)]
@@ -46,6 +45,7 @@ use cranelift_codegen::isa::TargetIsa;
 use cranelift_codegen::settings::{self, Configurable};
 use rustc_codegen_ssa::traits::CodegenBackend;
 use rustc_codegen_ssa::{CodegenResults, TargetConfig};
+use rustc_log::tracing::info;
 use rustc_middle::dep_graph::{WorkProduct, WorkProductId};
 use rustc_session::Session;
 use rustc_session::config::OutputFilenames;

compiler/rustc_codegen_gcc/src/back/lto.rs

@@ -30,6 +30,7 @@ use rustc_codegen_ssa::traits::*;
 use rustc_codegen_ssa::{ModuleCodegen, ModuleKind, looks_like_rust_object_file};
 use rustc_data_structures::memmap::Mmap;
 use rustc_errors::DiagCtxtHandle;
+use rustc_log::tracing::info;
 use rustc_middle::bug;
 use rustc_middle::dep_graph::WorkProduct;
 use rustc_session::config::Lto;

compiler/rustc_codegen_gcc/src/back/write.rs

@@ -5,6 +5,7 @@ use rustc_codegen_ssa::back::link::ensure_removed;
 use rustc_codegen_ssa::back::write::{BitcodeSection, CodegenContext, EmitObj, ModuleConfig};
 use rustc_codegen_ssa::{CompiledModule, ModuleCodegen};
 use rustc_fs_util::link_or_copy;
+use rustc_log::tracing::debug;
 use rustc_session::config::OutputType;
 use rustc_target::spec::SplitDebuginfo;
 

compiler/rustc_codegen_gcc/src/consts.rs

@@ -8,6 +8,7 @@ use rustc_codegen_ssa::traits::{
 use rustc_hir::attrs::Linkage;
 use rustc_hir::def::DefKind;
 use rustc_hir::def_id::LOCAL_CRATE;
+use rustc_log::tracing::trace;
 use rustc_middle::middle::codegen_fn_attrs::{CodegenFnAttrFlags, CodegenFnAttrs};
 use rustc_middle::mir::interpret::{
     self, ConstAllocation, ErrorHandled, Scalar as InterpScalar, read_target_uint,

compiler/rustc_codegen_gcc/src/gcc_util.rs

@@ -1,8 +1,8 @@
 #[cfg(feature = "master")]
 use gccjit::Context;
 use rustc_codegen_ssa::target_features;
+use rustc_data_structures::smallvec::{SmallVec, smallvec};
 use rustc_session::Session;
-use smallvec::{SmallVec, smallvec};
 
 fn gcc_features_by_flags(sess: &Session, features: &mut Vec<String>) {
     target_features::retpoline_features_by_flags(sess, features);

compiler/rustc_codegen_gcc/src/lib.rs

@@ -25,12 +25,6 @@
 #![deny(clippy::pattern_type_mismatch)]
 #![allow(clippy::needless_lifetimes, clippy::uninlined_format_args)]
 
-// These crates are pulled from the sysroot because they are part of
-// rustc's public API, so we need to ensure version compatibility.
-extern crate smallvec;
-#[macro_use]
-extern crate tracing;
-
 // The rustc crates we need
 extern crate rustc_abi;
 extern crate rustc_apfloat;
@@ -44,6 +38,7 @@ extern crate rustc_hir;
 extern crate rustc_index;
 #[cfg(feature = "master")]
 extern crate rustc_interface;
+extern crate rustc_log;
 extern crate rustc_macros;
 extern crate rustc_middle;
 extern crate rustc_session;

compiler/rustc_data_structures/src/lib.rs

@@ -44,6 +44,8 @@ use std::fmt;
 pub use atomic_ref::AtomicRef;
 pub use ena::{snapshot_vec, undo_log, unify};
 pub use rustc_index::static_assert_size;
+// Re-export some data-structure crates which are part of our public API.
+pub use {either, indexmap, smallvec, thin_vec};
 
 pub mod aligned;
 pub mod base_n;

compiler/rustc_lint/messages.ftl

@@ -325,6 +325,9 @@ lint_impl_trait_overcaptures = `{$self_ty}` will capture more lifetimes than pos
 lint_impl_trait_redundant_captures = all possible in-scope parameters are already captured, so `use<...>` syntax is redundant
     .suggestion = remove the `use<...>` syntax
 
+lint_implicit_sysroot_crate_import = dangerous use of `extern crate {$name}` which is not guaranteed to exist exactly once in the sysroot
+    .help = try using a cargo dependency or using a re-export of the dependency provided by a rustc_* crate
+
 lint_implicit_unsafe_autorefs = implicit autoref creates a reference to the dereference of a raw pointer
     .note = creating a reference requires the pointer target to be valid and imposes aliasing requirements
     .raw_ptr = this raw pointer has type `{$raw_ptr_ty}`

compiler/rustc_lint/src/internal.rs

@@ -12,10 +12,10 @@ use tracing::debug;
 use {rustc_ast as ast, rustc_hir as hir};
 
 use crate::lints::{
-    BadOptAccessDiag, DefaultHashTypesDiag, DiagOutOfImpl, LintPassByHand,
-    NonGlobImportTypeIrInherent, QueryInstability, QueryUntracked, SpanUseEqCtxtDiag,
-    SymbolInternStringLiteralDiag, TyQualified, TykindDiag, TykindKind, TypeIrDirectUse,
-    TypeIrInherentUsage, TypeIrTraitUsage, UntranslatableDiag,
+    BadOptAccessDiag, DefaultHashTypesDiag, DiagOutOfImpl, ImplicitSysrootCrateImportDiag,
+    LintPassByHand, NonGlobImportTypeIrInherent, QueryInstability, QueryUntracked,
+    SpanUseEqCtxtDiag, SymbolInternStringLiteralDiag, TyQualified, TykindDiag, TykindKind,
+    TypeIrDirectUse, TypeIrInherentUsage, TypeIrTraitUsage, UntranslatableDiag,
 };
 use crate::{EarlyContext, EarlyLintPass, LateContext, LateLintPass, LintContext};
 
@@ -745,3 +745,40 @@ impl<'tcx> LateLintPass<'tcx> for SymbolInternStringLiteral {
         }
     }
 }
+
+declare_tool_lint! {
+    /// The `implicit_sysroot_crate_import` detects use of `extern crate` to import non-sysroot crates
+    /// (e.g. crates.io deps) from the sysroot, which is dangerous because these crates are not guaranteed
+    /// to exist exactly once, and so may be missing entirely or appear multiple times resulting in ambiguity.
+    pub rustc::IMPLICIT_SYSROOT_CRATE_IMPORT,
+    Allow,
+    "Forbid uses of non-sysroot crates in `extern crate`",
+    report_in_external_macro: true
+}
+
+declare_lint_pass!(ImplicitSysrootCrateImport => [IMPLICIT_SYSROOT_CRATE_IMPORT]);
+
+impl EarlyLintPass for ImplicitSysrootCrateImport {
+    fn check_item(&mut self, cx: &EarlyContext<'_>, item: &ast::Item) {
+        fn is_whitelisted(crate_name: &str) -> bool {
+            // Whitelist of allowed crates.
+            crate_name.starts_with("rustc_")
+                || matches!(
+                    crate_name,
+                    "test" | "self" | "core" | "alloc" | "std" | "proc_macro" | "tikv_jemalloc_sys"
+                )
+        }
+
+        if let ast::ItemKind::ExternCrate(original_name, imported_name) = &item.kind {
+            let name = original_name.as_ref().unwrap_or(&imported_name.name).as_str();
+            let externs = &cx.builder.sess().opts.externs;
+            if externs.get(name).is_none() && !is_whitelisted(name) {
+                cx.emit_span_lint(
+                    IMPLICIT_SYSROOT_CRATE_IMPORT,
+                    item.span,
+                    ImplicitSysrootCrateImportDiag { name },
+                );
+            }
+        }
+    }
+}